Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
-    "down_proj",
     "up_proj",
     "o_proj",
-    "k_proj",
-    "q_proj"
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43da2a1eb2790fe62f293e01d8ada013a0d966df4f2ada2660b9a71af9f5002a
+oid sha256:c3e79621ffc14fb91a39d698499c2cb759cf1caea21cf010b8e80340ac6a5721
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39701fa216f95fd1e0171751e98aa83608c72ac9eb0c890e4ab69484314eeeed
+oid sha256:6f6c2ef00fa3cffe1608f2bcd6476e992598cc48a8279a6f80478bfff85bff11
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13893f254074b0dec5e8003565583ed9154abab49baf146f6045b5d48206e343
+oid sha256:413baf801b6b282f4a4f8a102791a0e43f3596f80253ee4e57b1d684a62cbb52
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,130 +1,63 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21052631578947367,
-  "eval_steps": 2,
-  "global_step": 10,
+  "epoch": 0.05263157894736842,
+  "eval_steps": 3,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.021052631578947368,
-      "grad_norm": 0.7498180866241455,
+      "epoch": 0.010526315789473684,
+      "grad_norm": 0.7775679230690002,
       "learning_rate": 2e-05,
-      "loss": 1.2983,
+      "loss": 1.3487,
       "step": 1
     },
     {
-      "epoch": 0.021052631578947368,
-      "eval_loss": 1.2585705518722534,
-      "eval_runtime": 15.0051,
-      "eval_samples_per_second": 6.664,
-      "eval_steps_per_second": 0.666,
+      "epoch": 0.010526315789473684,
+      "eval_loss": 1.281607985496521,
+      "eval_runtime": 13.6651,
+      "eval_samples_per_second": 7.318,
+      "eval_steps_per_second": 1.464,
       "step": 1
     },
     {
-      "epoch": 0.042105263157894736,
-      "grad_norm": 0.7510321736335754,
+      "epoch": 0.021052631578947368,
+      "grad_norm": 1.099178671836853,
       "learning_rate": 4e-05,
-      "loss": 1.4576,
-      "step": 2
-    },
-    {
-      "epoch": 0.042105263157894736,
-      "eval_loss": 1.2596663236618042,
-      "eval_runtime": 15.033,
-      "eval_samples_per_second": 6.652,
-      "eval_steps_per_second": 0.665,
+      "loss": 1.2265,
       "step": 2
     },
     {
-      "epoch": 0.06315789473684211,
-      "grad_norm": 0.6777486801147461,
+      "epoch": 0.031578947368421054,
+      "grad_norm": 0.8365464806556702,
       "learning_rate": 6e-05,
-      "loss": 1.2738,
+      "loss": 1.2875,
       "step": 3
     },
     {
-      "epoch": 0.08421052631578947,
-      "grad_norm": 0.7081015706062317,
-      "learning_rate": 8e-05,
-      "loss": 1.4211,
-      "step": 4
+      "epoch": 0.031578947368421054,
+      "eval_loss": 1.2764880657196045,
+      "eval_runtime": 13.7342,
+      "eval_samples_per_second": 7.281,
+      "eval_steps_per_second": 1.456,
+      "step": 3
     },
     {
-      "epoch": 0.08421052631578947,
-      "eval_loss": 1.2397140264511108,
-      "eval_runtime": 15.0876,
-      "eval_samples_per_second": 6.628,
-      "eval_steps_per_second": 0.663,
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.7803714871406555,
+      "learning_rate": 8e-05,
+      "loss": 1.6142,
       "step": 4
     },
     {
-      "epoch": 0.10526315789473684,
-      "grad_norm": 0.5160530805587769,
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.7291099429130554,
       "learning_rate": 0.0001,
-      "loss": 1.2373,
+      "loss": 1.2196,
       "step": 5
-    },
-    {
-      "epoch": 0.12631578947368421,
-      "grad_norm": 0.5380682349205017,
-      "learning_rate": 0.00012,
-      "loss": 1.3893,
-      "step": 6
-    },
-    {
-      "epoch": 0.12631578947368421,
-      "eval_loss": 1.2157351970672607,
-      "eval_runtime": 15.0706,
-      "eval_samples_per_second": 6.635,
-      "eval_steps_per_second": 0.664,
-      "step": 6
-    },
-    {
-      "epoch": 0.14736842105263157,
-      "grad_norm": 0.6841205358505249,
-      "learning_rate": 0.00014,
-      "loss": 1.3356,
-      "step": 7
-    },
-    {
-      "epoch": 0.16842105263157894,
-      "grad_norm": 0.4957394599914551,
-      "learning_rate": 0.00016,
-      "loss": 1.2216,
-      "step": 8
-    },
-    {
-      "epoch": 0.16842105263157894,
-      "eval_loss": 1.2087069749832153,
-      "eval_runtime": 15.1596,
-      "eval_samples_per_second": 6.596,
-      "eval_steps_per_second": 0.66,
-      "step": 8
-    },
-    {
-      "epoch": 0.18947368421052632,
-      "grad_norm": 0.5728506445884705,
-      "learning_rate": 0.00018,
-      "loss": 1.2016,
-      "step": 9
-    },
-    {
-      "epoch": 0.21052631578947367,
-      "grad_norm": 0.4859888255596161,
-      "learning_rate": 0.0002,
-      "loss": 1.3764,
-      "step": 10
-    },
-    {
-      "epoch": 0.21052631578947367,
-      "eval_loss": 1.1915773153305054,
-      "eval_runtime": 15.0938,
-      "eval_samples_per_second": 6.625,
-      "eval_steps_per_second": 0.663,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -139,13 +72,13 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 9677225695641600.0,
-  "train_batch_size": 10,
+  "total_flos": 2419306423910400.0,
+  "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d505e03c87584f88db69c68d4d3c92d4afd1945e9110366729a610299a3612d8
+oid sha256:166abb0c7e40600a59b0bdee3ffd387689a238ce61ab902f8e45f70ef598ee44
 size 6648